Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/paulrberg/foundry-template/agents-mdgit clone --depth 1 https://github.com/PaulRBerg/foundry-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/paulrberg/foundry-template/agents-md)<a href="https://agentmods.dev/instructions/paulrberg/foundry-template/agents-md"><img src="https://agentmods.dev/badge/instructions/paulrberg/foundry-template/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01484 | $0.01484 |
| Opus 5 | $0.00742 | $0.00742 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade C, and why
foundry-template AGENTS.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `bun run clean` — `rm -rf cache out` How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Foundry-based template for developing Solidity smart contracts. Dependencies are managed as Node.js packages (via Bun)
and remapped through remappings.txt instead of git submodules.
Stack
- Solidity
0.8.29(pragma>=0.8.29), EVM targetshanghai, optimizer on (10,000 runs) - Foundry (
forge) — compile, test, fuzz, format, deploy - Forge Std
v1.9.7— test and scripting framework - OpenZeppelin Contracts
5.3.0— pre-installed contract library - Bun — dependency manager (deps installed as Node.js packages, remapped in
remappings.txt) - Prettier
3.5— formatter for JSON/Markdown/YAML - Solhint
5.1— Solidity linter
Commands
Forge
forge build— compile contractsforge build --sizes— compile and print contract sizes (CI build step)forge test— run the test suiteforge test -vvv— run tests withconsole2logs shownforge test --gas-report— run tests with a gas reportforge coverage— generate a coverage reportforge fmt— format Solidityforge fmt --check— check Solidity formatting without writingforge clean— deleteout/andcache/forge config— print the resolved Foundry configforge script script/Deploy.s.sol --broadcast --fork-url http://localhost:8545— deployFooto a local node (requiresMNEMONICorETH_FROM)forge script script/DeployBrowser.s.sol --broadcast --fork-url http://localhost:8545 --browser— deployFooto a local node (requires you to connect your wallet at localhost:9545)
Bun scripts (package.json)
bun install— install Node.js dependencies (add a matching entry toremappings.txtafterward)bun run build—forge buildbun run test—forge testbun run clean—rm -rf cache outbun run forge-check—forge fmt --checkbun run forge-write—forge fmtbun run solhint-check— Solhint over{script,src,tests}/**/*.solbun run prettier:check— Prettier check over**/*.{json,md,yml}bun run prettier:write— Prettier write over**/*.{json,md,yml}bun run full-check—forge-check+solhint-check+prettier:check(the CI lint gate)bun run full-write—forge-write+prettier:write(auto-fix formatting)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 92 lines · 1,484 tokens per session scan C 45ade8b2b2e9
foundry-template AGENTS.md is an instructions file published in the GitHub repository PaulRBerg/foundry-template (645 stars, last pushed 1mo ago), licensed MIT. It adds 1,484 tokens to every session, about $0.0074 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
prb-math AGENTS.md
Instructions for PaulRBerg/prb-math, covering prbmath, stack, structure, commands and development.
lineth-monorepo AGENTS.md
AGENTS.md instructions for LFDT-Lineth/lineth-monorepo, covering agents.md, documentation precedence, agent entry points, local agent workflows and discoverability index.
lineth-monorepo CLAUDE.md
Claude Code instructions for LFDT-Lineth/lineth-monorepo, covering claude.md, purpose, precedence, discoverability and note.
lineth-monorepo copilot-instructions.md
Copilot instructions for LFDT-Lineth/lineth-monorepo, covering github copilot instructions, purpose, precedence, discoverability and note.
PROGRAMMABLE AGENTS.md
AGENTS.md instructions for programmablehq/PROGRAMMABLE, covering programmable workspace rules, canonical repository, parallel work, path ownership and release discipline.
prb-math CLAUDE.md
Instructions for PaulRBerg/prb-math, a project described as: Solidity library for advanced fixed-point math.